English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Nowadays, with the rising number of sensors in sectors such as healthcare andindustry, the problem of multivariate time series classification (MTSC) isgetting increasingly relevant and is a prime target for machine and deeplearning approaches. Their expanding adoption in real-world environments iscausing a shift in focus from the pursuit of ever-higher prediction accuracywith complex models towards practical, deployable solutions that balanceaccuracy and parameters such as prediction speed. An MTSC model that hasattracted attention recently is ROCKET, based on random convolutional kernels,both because of its very fast training process and its state-of-the-artaccuracy. However, the large number of features it utilizes may be detrimentalto inference time. Examining its theoretical background and limitations enablesus to address potential drawbacks and present LightWaveS: a framework foraccurate MTSC, which is fast both during training and inference. Specifically,utilizing wavelet scattering transformation and distributed feature selection,we manage to create a solution that employs just 2.5% of the ROCKET features,while achieving accuracy comparable to recent MTSC models. LightWaveS alsoscales well across multiple compute nodes and with the number of input channelsduring training. In addition, it can significantly reduce the input size andprovide insight to an MTSC problem by keeping only the most useful channels. Wepresent three versions of our algorithm and their results on distributedtraining time and scalability, accuracy, and inference speedup. We show that weachieve speedup ranging from 9x to 53x compared to ROCKET during inference onan edge device, on datasets with comparable accuracy.

Taking ROCKET on an Efficiency Mission: Multivariate Time Series Classification with LightWaveS